Stochastic Linear Quadratic Optimal Control Problem: A Reinforcement Learning Method
From MaRDI portal
Abstract: This paper applies a reinforcement learning (RL) method to solve infinite horizon continuous-time stochastic linear quadratic problems, where drift and diffusion terms in the dynamics may depend on both the state and control. Based on Bellman's dynamic programming principle, an online RL algorithm is presented to attain the optimal control with just partial system information. This algorithm directly computes the optimal control rather than estimating the system coefficients and solving the related Riccati equation. It just requires local trajectory information, greatly simplifying the calculation processing. Two numerical examples are carried out to shed light on our theoretical findings.
Cited in
(29)- Simplified optimized control using reinforcement learning algorithm for a class of stochastic nonlinear systems
- Linear-quadratic stochastic delayed control and deep learning resolution
- Minimax Q-learning control for linear systems using the Wasserstein metric
- Linear quadratic tracking control of unknown systems: a two-phase reinforcement learning method
- Reinforcement learning for exploratory linear-quadratic two-person zero-sum stochastic differential games
- Linear quadratic optimal learning control (LQL)
- Stochastic \varepsilon-Optimal Linear Quadratic Adaptation: An Alternating Controls Policy
- A Q-Learning Algorithm for Discrete-Time Linear-Quadratic Control with Random Parameters of Unknown Distribution: Convergence and Stabilization
- Primal-Dual Q-Learning Framework for LQR Design
- Reinforcement Learning for Adaptive Optimal Stationary Control of Linear Stochastic Systems
- Incremental reinforcement learning and optimal output regulation under unmeasurable disturbances
- Data-driven policy iteration algorithm for continuous-time stochastic linear-quadratic optimal control problems
- Solving optimal predictor-feedback control using approximate dynamic programming
- Mean field LQG social optimization: a reinforcement learning approach
- Model-free approximate dynamic programming for stochastic zero-sum games: algorithm design and analysis
- Stochastic linear quadratic optimal control for continuous-time systems via reinforcement learning
- Secure optimal control of Itô stochastic Markov jump systems subject to DoS attacks: a hybrid learning algorithm
- Data-driven control for stochastic linear-quadratic optimal problem with completely unknown dynamics
- Model-free H_ control of Itô stochastic system via off-policy reinforcement learning
- An online Q-learning method for linear-quadratic nonzero-sum stochastic differential games with completely unknown dynamics
- On-policy and off-policy value iteration algorithms for stochastic zero-sum dynamic games
- Two system transformation data-driven algorithms for linear quadratic mean-field games
- Scaling policy iteration based reinforcement learning for unknown discrete-time linear systems
- Partially observed linear quadratic stochastic optimal control problem in infinite horizon: a data-driven approach
- Convergence of policy gradient for stochastic linear quadratic optimal control problems in infinite horizon
- System transformation and model-free value iteration algorithms for continuous-time linear quadratic stochastic optimal control problems
- Stochastic H₂/H_ off-policy reinforcement learning tracking control for linear discrete-time systems with multiplicative noises
- Adaptive optimal control of unknown stochastic discrete-time linear systems
- An online value iteration method for stochastic linear quadratic control with multiplicative noise
This page was built for publication: Stochastic Linear Quadratic Optimal Control Problem: A Reinforcement Learning Method
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6076047)
